def train(self, X, y, domain, featurizer, **kwargs):
if not utils.is_training_data_empty(X):
for policy in self.policies:
policy.prepare(featurizer, max_history=X.shape[1])
policy.train(X, y, domain, **kwargs)
else:
logger.info("Skipped training, because there are no "
"training samples.")
def _deduplicate_training_data(X, y):
# type: (ndarray, ndarray) -> Tuple[ndarray, ndarray]
"""Make sure every training example in X occurs exactly once."""
# we need to concat X and y to make sure that
# we do NOT throw out contradicting examples
# (same featurization but different labels).
# appends y to X so it appears to be just another feature
if not utils.is_training_data_empty(X):
casted_y = np.broadcast_to(np.reshape(y, (y.shape[0], 1, 1)),
(y.shape[0], X.shape[1], 1))
concatenated = np.concatenate((X, casted_y), axis=2)
t_data = np.unique(concatenated, axis=0)
X_unique = t_data[:, :, :-1]
y_unique = np.array(t_data[:, 0, -1], dtype=casted_y.dtype)
return X_unique, y_unique
else:
return X, y
def is_empty(self):
return utils.is_training_data_empty(self.X)
